The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external project data by scanning and reading index.ts and index.js files. While this represents a surface for indirect prompt injection if a source file contains malicious instructions, it is a standard functional requirement for a code maintenance tool.
[COMMAND_EXECUTION]: The skill is authorized to perform recursive directory scans and file modifications (reading and writing) specifically for the purpose of managing barrel exports. These operations are restricted to the project scope and align with the tool's primary utility.

check-barrel-export